{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCXC2ZVCJZRC2DT6HPFORV2BA6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35e518b7d2a8d9cf8cf6fe901380afec54654a0fafc9f27ee83f3a4a4c6b1173","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:48:45Z","title_canon_sha256":"9796c6ad2cdd85059bfaa40dc8c97072c526a6b2261a041dac9308252f681991"},"schema_version":"1.0","source":{"id":"2310.10625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10625","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10625v1","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10625","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"PCXC2ZVCJZRC","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"PCXC2ZVCJZRC2DT6","created_at":"2026-07-05T07:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"PCXC2ZVC","created_at":"2026-07-05T07:01:22Z"}],"graph_snapshots":[{"event_id":"sha256:b8b69a9692238785703f4d43f6704410a1b91ea8d4aa10aa2a1ea6964d5fb3ca","target":"graph","created_at":"2026-07-05T07:01:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.10625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We are interested in enabling visual planning for complex long-horizon tasks in the space of generated videos and language, leveraging recent advances in large generative models pretrained on Internet-scale data. To this end, we present video language planning (VLP), an algorithm that consists of a tree search procedure, where we train (i) vision-language models to serve as both policies and value functions, and (ii) text-to-video models as dynamics models. VLP takes as input a long-horizon task instruction and current image observation, and outputs a long video plan that provides detailed mul","authors_text":"Andy Zeng, Ayzaan Wahid, Brian Ichter, Fei Xia, Jonathan Tompson, Joshua B. Tenenbaum, Leslie Kaelbling, Mengjiao Yang, Pete Florence, Pierre Sermanet, Pieter Abbeel, Tianhe Yu, Yilun Du","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:48:45Z","title":"Video Language Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10625","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9b67746f012651011f3956af2c94a3c75b571b3bfc4e70cc56cb03a918f5345e","target":"record","created_at":"2026-07-05T07:01:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35e518b7d2a8d9cf8cf6fe901380afec54654a0fafc9f27ee83f3a4a4c6b1173","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-16T17:48:45Z","title_canon_sha256":"9796c6ad2cdd85059bfaa40dc8c97072c526a6b2261a041dac9308252f681991"},"schema_version":"1.0","source":{"id":"2310.10625","kind":"arxiv","version":1}},"canonical_sha256":"78ae2d66a24e622d0e7e3bcae8d74107b7cedc81be38f4f030e569b751646774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78ae2d66a24e622d0e7e3bcae8d74107b7cedc81be38f4f030e569b751646774","first_computed_at":"2026-07-05T07:01:22.527006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:22.527006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pEu8prYa4NTXk4tfT4PKxeixCag2nedrA6ozFK2wVVkuaENv49QtFNfA+0KP66UiLCxClPax5lw3KQ2O57JLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:22.527521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b67746f012651011f3956af2c94a3c75b571b3bfc4e70cc56cb03a918f5345e","sha256:b8b69a9692238785703f4d43f6704410a1b91ea8d4aa10aa2a1ea6964d5fb3ca"],"state_sha256":"cb542e1f5480db3ee7dc4822d8ea3e5eb1d2ddb085fc300efab64f02c6a9dc4a"}